© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8311
    Prev
    Next
    INDEX
    Explanations

    structured data formats and programming-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, structs, and marshaling within a program

    np_acts-logits-general · gemini-2.0-flash

    json and go structs for data or requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    []
    -0.70
    peutic
    -0.52
     mete
    -0.50
    [],
    -0.50
    انجليز
    -0.49
    +#+#
    -0.49
    balleur
    -0.49
     &
    -0.49
     []
    -0.48
     comport
    -0.47
    POSITIVE LOGITS
    出版年
    0.59
    舺
    0.57
     Chriftian
    0.56
    béco
    0.55
     ――――――――
    0.54
    EndInit
    0.54
     Baillargeon
    0.54
    neſs
    0.54
     Rabu
    0.54
    initComponents
    0.52
    Activations Density 0.226%

    No Known Activations